Abstract

This paper proposes a method to recognize dialect on personal computers. Proposal method pays attention to dialects’ emotion content of speakers. Dialects have much emotional expression compared with standard dialect. Therefore, this system judges sentences including some dialects using Emotion Judgment System inputting dialects as standard dialects. Emotion Judgment System answers wrong emotion as standard dialect if inputs include some dialect. This paper treats dialect used in Nagano prefecture, Japan. This paper shows that using speaker’s emotion can solve the disambiguation of the dialect and the standard dialect.

Keywords

Morphological Analysis Emotion Content Proposal Method Word Sense Disambiguation Unknown Word 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Yarowsky, D.: Word-sense disambiguation using statistical models of Roget’s categories trained on large corpora. In: Proc. COLING 1992, pp. 454–460 (1992)Google Scholar
  2. 2.
    Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: Proc. ACL 1995, pp. 189–196 (1995)Google Scholar
  3. 3.
    Veronis, J., Ide, N.: Word sense disambiguation with very large neural networks extracted from machine readable dictionaries. In: Proc. COLING 1992, pp. 359–365 (1992)Google Scholar
  4. 4.
    Noriyuki, O., et al.: An Association Method Using Concept-base. In: Apolloni, B., Howlett, R.J., Jain, L. (eds.) KES 2007, Part I. LNCS (LNAI), vol. 4692, pp. 604–611. Springer, Heidelberg (2007)Google Scholar
  5. 5.
    Seiji, T., et al.: Proposal of Method to Judge Speaker’s Emotion Based on Association Mechanism. In: Apolloni, B., Howlett, R.J., Jain, L. (eds.) KES 2007, Part I. LNCS (LNAI), vol. 4692, pp. 847–854. Springer, Heidelberg (2007)Google Scholar
  6. 6.
    Taku, K., et al.: Applying Conditional Random Fields to Japanese Morphological Analysis. In: Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP 2004), pp. 230–237 (2004)Google Scholar
  7. 7.
    The National Language Research Institute, Tokyo, Japan: Texts of Tape-Recorded Conversation In Japanese Dialects, vol. 1 (1978)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Noriyuki Okumura
    • 1
  1. 1.Department of Electronics and Information ScienceNagano National College of TechnologyNaganoJapan

Personalised recommendations